Why this obsession with "replacement" instead of tooling?
Replacing my best friends with an LLM trained on 500k group chat messages
131–140 of 371 posts
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#132Very reminiscent of the Be Right Back episode of Black Mirror [1]. A family member recently died unexpectedly, and I have a small collection of texts, emails, and blog posts by them saved on my machine in the small (perhaps delusional) hope that they'll be a useful training set for a them-flavored chatbot. Perhaps even one that's trained to help me with the grief of their loss. Not a huge amount of training data, tho…
This feels very dark to me: I think it would make it enormously harder to actually process the grief. (The thought "You could make one to mimic your ex" passed through my head just long enough for me to recoil in absolute horror.)
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#133While I love all these stories of turning your friends and loved ones into chat bots so you can talk to them forever, my brain immediately took a much darker turn because of course it did. How many emails, text messages, hangouts/gchat messages, etc, does Google have of you right now? And as part of their agreement, they can do pretty much whatever they like with those, can't they? Could Google, or any other company…
relevant krazam: https://youtu.be/BrQyMrmRBsk
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#134Great write up, thanks for posting. I’ve been thinking of doing this for myself. One thought that’s haunting: how long before AI friends are more interesting and stimulating than any real person would be, leading people to prefer AI over humans to befriend… Super stimulus to end all super stimuluses?
This is a concept in the sci-fi book The Mountain in the Sea, where people have "point-fives" (as in 0.5) -- AI companions custom-tailored to be the ideal zero-effort-required friend for you.
In the book, it starts from someone jokingly observing that many people don't want a full relationship, with 2 full people learning one another and being there for each other -- instead, many people want just the easy/fun parts of a relationship: they want something with 1.5 people, where they get to be the 1 "full person" and the other person is only 0.5 of a person, able to make you happy or satisfy your wants and needs while never asking anything of you in return and never having any needs of their own.
Then some unnamed tech company in the scifi-future-geography "SF-SD Axis" (sounds like San Francisco to me) builds and product-izes that, at first pitching it as a therapy/rehab tool, but eventually expanding it out until they're more ubiquitous and many people have isolated themselves to only having their "point-five" as a close friend. One character observes "I think this is the longest conversation I've had with a real person in years" after talking with another person for an hour or two.
I haven't finished the book, so I don't know how that plays out, but as someone who believes firmly in humans' need for community (including, at times, _uncomfortable_ community), that concept was chilling against the backdrop of ChatGPT/LLM headlines.
Imagine all the isolation problems of today, along with all the mess of internet-anonymity-as-replacement-for-friendships that exist today -- but cranked to 11 as you no longer even have to seek out other humans who share your niche views (redpill, incel, neonazi, you name it), because now you can just interact with sufficiently-realistic simulations of people designed to reinforce all your own thoughts back to you.
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#135I've actually been working on something similar for the Discord server I have with my friends. Fun to see others doing something similar! It's very funny to mess around with.
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#136> On a technical level, I found it really helped me wrap my head around what LLMs are doing and how they can be tuned for specific scenarios.
LMAO, noob!
(I guess people don't like when a reply in the tone the OP's friends is posted.)
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#137This is one of the best, most detailed write-ups of how to fine-train a large language model on custom text that I've seen anywhere.
Thank you!! I felt it was getting so long and was worried it would be impenetrable, so I'm really pleased to hear it felt great.
Really great!
With Alpaca-Lora 4-bit training getting usable any day now it should get a lot more affordable or you can even do it at home.
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#138Wish I had friends who talked mild shit like this! All my friends are nerds who take everything seriously. On the project, did you do anything about the time dimension? ChatGPT is strictly input -> output, but something like this needs time between messages to feel real (and not run constantly). I imagine adding "time since last message" to the training data + expected output would work.
wow. did you just call out your friends for being nerdy and say the nerdiest thing I've ever heard? Not that it's not a cool idea, though.
Pot calling the kettle dork lol
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#139I’m almost at the point where i don’t want to use the internet anymore.
Re: Replacing my best friends with an LLM trained on 500k group chat messages
#140Earlier quoted context omitted.
For all the fears of AGI, these are the more concrete nefarious uses we can actually reason about. It is a point I often make that we don't need AGI for AI to already become very disturbing in its potential use. The other point, is that technically this AI is not "unaligned". It is doing exactly what is requested of the operator. The implications are that humanity suffers in either scenario, either by our own agency…
> It is a point I often make that we don't need AGI for AI to already become very disturbing in its potential use. But we don't need AI or LLMs at all for the above scenario. Companies don't currently pry into your e-mails to make hiring decisions, but they could (ignoring laws) do it if they wanted. No LLM or AI necessary. So why would the existence of AIs or LLMs change that? If they wanted to use the content of yo…
Running an authoritarian police state is risky because of all the people involved in the authoritarian police state, also it's massively expensive to keep all those people snooping and you have to take them out and kill them on occasion because they learn too much.
But wait, you can just dump that information into a superAIcomputer and get reliable enough results while not needing a break with little to no risk of the computer rising up against you. Sounds like a hell of a deal.
Quantity is a quality in itself.